AIThe Decoderabout 3 hours ago
Anthropic Opus 5 tops ARC-AGI-3 benchmark
1 min read
Anthropic's Claude Opus 5 scored 30.2 percent on ARC-AGI-3, nearly quadrupling GPT-5.6 Sol's previous record of 7.8 percent. The model independently formulated reflection equations, a behavior unseen from other models.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyAnthropic
Summary by ByteBrief
